Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4307 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1236. Min Range: -6.1236
Max Act: 6.1236. Min Act: -0.1700
Data Index: 4164194 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.9674. Min Act: -0.1700
Data Index: 6774062 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.9986. Min Act: -0.1700
Data Index: 4518205 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.9049. Min Act: -0.1700
Data Index: 1339384 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.8736. Min Act: -0.1700
Data Index: 5432076 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.8111. Min Act: -0.1700
Data Index: 7064671 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.7486. Min Act: -0.1700
Data Index: 8472470 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.7486. Min Act: -0.1700
Data Index: 155046 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6861. Min Act: -0.1700
Data Index: 3848604 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6549. Min Act: -0.1700
Data Index: 5719048 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 265842 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7646452 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7530547 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 1848006 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7653508 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.5611. Min Act: -0.1700
Data Index: 5208729 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.5611. Min Act: -0.1700
Data Index: 8169300 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.5299. Min Act: -0.1700
Data Index: 8146681 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.5299. Min Act: -0.1700
Data Index: 1632470 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1236. Min Range: -6.1236
Max Act: 5.4986. Min Act: -0.1700
Data Index: 1110047 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19